Skip to content

Add variant argument to dreambooth lora sdxl advanced #6021

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
patrickvonplaten merged 2 commits into from
Dec 4, 2023
Merged

Add variant argument to dreambooth lora sdxl advanced #6021

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b39c848
Add variant argument to dreambooth lora sdxl advanced
levi Dec 1, 2023
cff6b2e
Merge branch 'main' into levi/advanced-variant
sayakpaul Dec 4, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 39 additions & 9 deletions examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,6 +225,12 @@ def parse_args(input_args=None):
required=False,
help="Revision of pretrained model identifier from huggingface.co/models.",
)
parser.add_argument(
"--variant",
type=str,
default=None,
help="Variant of the model files of the pretrained model identifier from huggingface.co/models, 'e.g.' fp16",
)
parser.add_argument(
"--dataset_name",
type=str,
Expand Down Expand Up @@ -1064,6 +1070,7 @@ def main(args):
args.pretrained_model_name_or_path,
torch_dtype=torch_dtype,
revision=args.revision,
variant=args.variant,
)
pipeline.set_progress_bar_config(disable=True)

Expand Down Expand Up @@ -1102,10 +1109,18 @@ def main(args):

# Load the tokenizers
tokenizer_one = AutoTokenizer.from_pretrained(
args.pretrained_model_name_or_path, subfolder="tokenizer", revision=args.revision, use_fast=False
args.pretrained_model_name_or_path,
subfolder="tokenizer",
revision=args.revision,
variant=args.variant,
use_fast=False,
)
tokenizer_two = AutoTokenizer.from_pretrained(
args.pretrained_model_name_or_path, subfolder="tokenizer_2", revision=args.revision, use_fast=False
args.pretrained_model_name_or_path,
subfolder="tokenizer_2",
revision=args.revision,
variant=args.variant,
use_fast=False,
)

# import correct text encoder classes
Expand All @@ -1119,21 +1134,24 @@ def main(args):
# Load scheduler and models
noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
text_encoder_one = text_encoder_cls_one.from_pretrained(
args.pretrained_model_name_or_path, subfolder="text_encoder", revision=args.revision
args.pretrained_model_name_or_path, subfolder="text_encoder", revision=args.revision, variant=args.variant
)
text_encoder_two = text_encoder_cls_two.from_pretrained(
args.pretrained_model_name_or_path, subfolder="text_encoder_2", revision=args.revision
args.pretrained_model_name_or_path, subfolder="text_encoder_2", revision=args.revision, variant=args.variant
)
vae_path = (
args.pretrained_model_name_or_path
if args.pretrained_vae_model_name_or_path is None
else args.pretrained_vae_model_name_or_path
)
vae = AutoencoderKL.from_pretrained(
vae_path, subfolder="vae" if args.pretrained_vae_model_name_or_path is None else None, revision=args.revision
vae_path,
subfolder="vae" if args.pretrained_vae_model_name_or_path is None else None,
revision=args.revision,
variant=args.variant,
)
unet = UNet2DConditionModel.from_pretrained(
args.pretrained_model_name_or_path, subfolder="unet", revision=args.revision
args.pretrained_model_name_or_path, subfolder="unet", revision=args.revision, variant=args.variant
)

if args.train_text_encoder_ti:
Expand Down Expand Up @@ -1843,10 +1861,16 @@ def compute_text_embeddings(prompt, text_encoders, tokenizers):
# create pipeline
if freeze_text_encoder:
text_encoder_one = text_encoder_cls_one.from_pretrained(
args.pretrained_model_name_or_path, subfolder="text_encoder", revision=args.revision
args.pretrained_model_name_or_path,
subfolder="text_encoder",
revision=args.revision,
variant=args.variant,
)
text_encoder_two = text_encoder_cls_two.from_pretrained(
args.pretrained_model_name_or_path, subfolder="text_encoder_2", revision=args.revision
args.pretrained_model_name_or_path,
subfolder="text_encoder_2",
revision=args.revision,
variant=args.variant,
)
pipeline = StableDiffusionXLPipeline.from_pretrained(
args.pretrained_model_name_or_path,
Expand All @@ -1855,6 +1879,7 @@ def compute_text_embeddings(prompt, text_encoders, tokenizers):
text_encoder_2=accelerator.unwrap_model(text_encoder_two),
unet=accelerator.unwrap_model(unet),
revision=args.revision,
variant=args.variant,
torch_dtype=weight_dtype,
)

Expand Down Expand Up @@ -1932,10 +1957,15 @@ def compute_text_embeddings(prompt, text_encoders, tokenizers):
vae_path,
subfolder="vae" if args.pretrained_vae_model_name_or_path is None else None,
revision=args.revision,
variant=args.variant,
torch_dtype=weight_dtype,
)
pipeline = StableDiffusionXLPipeline.from_pretrained(
args.pretrained_model_name_or_path, vae=vae, revision=args.revision, torch_dtype=weight_dtype
args.pretrained_model_name_or_path,
vae=vae,
revision=args.revision,
variant=args.variant,
torch_dtype=weight_dtype,
)

# We train on the simplified learning objective. If we were previously predicting a variance, we need the scheduler to ignore it
Expand Down